Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull rdma updates from Jason Gunthorpe:
 "A very quiet cycle with few notable changes. Mostly the usual list of
  one or two patches to drivers changing something that isn't quite rc
  worthy. The subsystem seems to be seeing a larger number of rework and
  cleanup style patches right now, I feel that several vendors are
  prepping their drivers for new silicon.

  Summary:

   - Driver updates and cleanup for qedr, bnxt_re, hns, siw, mlx5, mlx4,
     rxe, i40iw

   - Larger series doing cleanup and rework for hns and hfi1.

   - Some general reworking of the CM code to make it a little more
     understandable

   - Unify the different code paths connected to the uverbs FD scheme

   - New UAPI ioctls conversions for get context and get async fd

   - Trace points for CQ and CM portions of the RDMA stack

   - mlx5 driver support for virtio-net formatted rings as RDMA raw
     ethernet QPs

   - verbs support for setting the PCI-E relaxed ordering bit on DMA
     traffic connected to a MR

   - A couple of bug fixes that came too late to make rc7"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (108 commits)
  RDMA/core: Make the entire API tree static
  RDMA/efa: Mask access flags with the correct optional range
  RDMA/cma: Fix unbalanced cm_id reference count during address resolve
  RDMA/umem: Fix ib_umem_find_best_pgsz()
  IB/mlx4: Fix leak in id_map_find_del
  IB/opa_vnic: Spelling correction of 'erorr' to 'error'
  IB/hfi1: Fix logical condition in msix_request_irq
  RDMA/cm: Remove CM message structs
  RDMA/cm: Use IBA functions for complex structure members
  RDMA/cm: Use IBA functions for simple structure members
  RDMA/cm: Use IBA functions for swapping get/set acessors
  RDMA/cm: Use IBA functions for simple get/set acessors
  RDMA/cm: Add SET/GET implementations to hide IBA wire format
  RDMA/cm: Add accessors for CM_REQ transport_type
  IB/mlx5: Return the administrative GUID if exists
  RDMA/core: Ensure that rdma_user_mmap_entry_remove() is a fence
  IB/mlx4: Fix memory leak in add_gid error flow
  IB/mlx5: Expose RoCE accelerator counters
  RDMA/mlx5: Set relaxed ordering when requested
  RDMA/core: Add the core support field to METHOD_GET_CONTEXT
  ...

41 files changed, 1977 insertions, 972 deletions

diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index e7e8a0f49464..793c97251588 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -677,7 +677,7 @@ static int bnxt_re_register_ib(struct bnxt_re_dev *rdev)
 
 	bnxt_qplib_get_guid(rdev->netdev->dev_addr, (u8 *)&ibdev->node_guid);
 
-	ibdev->num_comp_vectors	= 1;
+	ibdev->num_comp_vectors	= rdev->num_msix - 1;
 	ibdev->dev.parent = &rdev->en_dev->pdev->dev;
 	ibdev->local_dma_lkey = BNXT_QPLIB_RSVD_LKEY;
 
diff --git a/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h b/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h
index e96bcb16bd2b..74b787a90660 100644
--- a/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h
+++ b/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h
@@ -160,10 +160,16 @@ struct efa_admin_create_qp_resp {
 	/* Common Admin Queue completion descriptor */
 	struct efa_admin_acq_common_desc acq_common_desc;
 
-	/* Opaque handle to be used for consequent operations on the QP */
+	/*
+	 * Opaque handle to be used for consequent admin operations on the
+	 * QP
+	 */
 	u32 qp_handle;
 
-	/* QP number in the given EFA virtual device */
+	/*
+	 * QP number in the given EFA virtual device. Least-significant bits
+	 *    (as needed according to max_qp) carry unique QP ID
+	 */
 	u16 qp_num;
 
 	/* MBZ */
@@ -286,6 +292,7 @@ struct efa_admin_create_ah_cmd {
 	/* PD number */
 	u16 pd;
 
+	/* MBZ */
 	u16 reserved;
 };
 
@@ -296,6 +303,7 @@ struct efa_admin_create_ah_resp {
 	/* Target interface address handle (opaque) */
 	u16 ah;
 
+	/* MBZ */
 	u16 reserved;
 };
 
@@ -372,6 +380,7 @@ struct efa_admin_reg_mr_cmd {
 	 */
 	u8 permissions;
 
+	/* MBZ */
 	u16 reserved16_w5;
 
 	/* number of pages in PBL (redundant, could be calculated) */
@@ -419,20 +428,20 @@ struct efa_admin_create_cq_cmd {
 	struct efa_admin_aq_common_desc aq_common_desc;
 
 	/*
-	 * 4:0 : reserved5
+	 * 4:0 : reserved5 - MBZ
 	 * 5 : interrupt_mode_enabled - if set, cq operates
 	 *    in interrupt mode (i.e. CQ events and MSI-X are
 	 *    generated), otherwise - polling
 	 * 6 : virt - If set, ring base address is virtual
 	 *    (IOVA returned by MR registration)
-	 * 7 : reserved6
+	 * 7 : reserved6 - MBZ
 	 */
 	u8 cq_caps_1;
 
 	/*
 	 * 4:0 : cq_entry_size_words - size of CQ entry in
 	 *    32-bit words, valid values: 4, 8.
-	 * 7:5 : reserved7
+	 * 7:5 : reserved7 - MBZ
 	 */
 	u8 cq_caps_2;
 
@@ -478,6 +487,7 @@ struct efa_admin_destroy_cq_cmd {
 
 	u16 cq_idx;
 
+	/* MBZ */
 	u16 reserved1;
 };
 
@@ -530,7 +540,7 @@ struct efa_admin_get_set_feature_common_desc {
 	/*
 	 * 1:0 : select - 0x1 - current value; 0x3 - default
 	 *    value
-	 * 7:3 : reserved3
+	 * 7:3 : reserved3 - MBZ
 	 */
 	u8 flags;
 
@@ -557,10 +567,10 @@ struct efa_admin_feature_device_attr_desc {
 	/* Bar used for SQ and RQ doorbells */
 	u16 db_bar;
 
-	/* Indicates how many bits are used physical address access */
+	/* Indicates how many bits are used on physical address access */
 	u8 phys_addr_width;
 
-	/* Indicates how many bits are used virtual address access */
+	/* Indicates how many bits are used on virtual address access */
 	u8 virt_addr_width;
 
 	/*
@@ -578,27 +588,28 @@ struct efa_admin_feature_queue_attr_desc {
 	/* The maximum number of queue pairs supported */
 	u32 max_qp;
 
+	/* Maximum number of WQEs per Send Queue */
 	u32 max_sq_depth;
 
-	/* max send wr used in inline-buf */
+	/* Maximum size of data that can be sent inline in a Send WQE */
 	u32 inline_buf_size;
 
+	/* Maximum number of buffer descriptors per Recv Queue */
 	u32 max_rq_depth;
 
 	/* The maximum number of completion queues supported per VF */
 	u32 max_cq;
 
+	/* Maximum number of CQEs per Completion Queue */
 	u32 max_cq_depth;
 
 	/* Number of sub-CQs to be created for each CQ */
 	u16 sub_cqs_per_cq;
 
+	/* MBZ */
 	u16 reserved;
 
-	/*
-	 * Maximum number of SGEs (buffs) allowed for a single send work
-	 *    queue element (WQE)
-	 */
+	/* Maximum number of SGEs (buffers) allowed for a single send WQE */
 	u16 max_wr_send_sges;
 
 	/* Maximum number of SGEs allowed for a single recv WQE */
diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c
index 4822f5fa12be..ec5545870554 100644
--- a/drivers/infiniband/hw/efa/efa_verbs.c
+++ b/drivers/infiniband/hw/efa/efa_verbs.c
@@ -387,8 +387,7 @@ static int efa_destroy_qp_handle(struct efa_dev *dev, u32 qp_handle)
 	return efa_com_destroy_qp(&dev->edev, &params);
 }
 
-static void efa_qp_user_mmap_entries_remove(struct efa_ucontext *uctx,
-					    struct efa_qp *qp)
+static void efa_qp_user_mmap_entries_remove(struct efa_qp *qp)
 {
 	rdma_user_mmap_entry_remove(qp->rq_mmap_entry);
 	rdma_user_mmap_entry_remove(qp->rq_db_mmap_entry);
@@ -398,8 +397,6 @@ static void efa_qp_user_mmap_entries_remove(struct efa_ucontext *uctx,
 
 int efa_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata)
 {
-	struct efa_ucontext *ucontext = rdma_udata_to_drv_context(udata,
-		struct efa_ucontext, ibucontext);
 	struct efa_dev *dev = to_edev(ibqp->pd->device);
 	struct efa_qp *qp = to_eqp(ibqp);
 	int err;
@@ -418,7 +415,7 @@ int efa_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata)
 				 DMA_TO_DEVICE);
 	}
 
-	efa_qp_user_mmap_entries_remove(ucontext, qp);
+	efa_qp_user_mmap_entries_remove(qp);
 	kfree(qp);
 	return 0;
 }
@@ -510,7 +507,7 @@ static int qp_mmap_entries_setup(struct efa_qp *qp,
 	return 0;
 
 err_remove_mmap:
-	efa_qp_user_mmap_entries_remove(ucontext, qp);
+	efa_qp_user_mmap_entries_remove(qp);
 
 	return -ENOMEM;
 }
@@ -719,7 +716,7 @@ struct ib_qp *efa_create_qp(struct ib_pd *ibpd,
 	return &qp->ibqp;
 
 err_remove_mmap_entries:
-	efa_qp_user_mmap_entries_remove(ucontext, qp);
+	efa_qp_user_mmap_entries_remove(qp);
 err_destroy_qp:
 	efa_destroy_qp_handle(dev, create_qp_resp.qp_handle);
 err_free_mapped:
@@ -1370,6 +1367,7 @@ struct ib_mr *efa_reg_mr(struct ib_pd *ibpd, u64 start, u64 length,
 		IB_ACCESS_LOCAL_WRITE |
 		(is_rdma_read_cap(dev) ? IB_ACCESS_REMOTE_READ : 0);
 
+	access_flags &= ~IB_ACCESS_OPTIONAL;
 	if (access_flags & ~supp_access_flags) {
 		ibdev_dbg(&dev->ibdev,
 			  "Unsupported access flags[%#x], supported[%#x]\n",
@@ -1608,13 +1606,12 @@ static int __efa_mmap(struct efa_dev *dev, struct efa_ucontext *ucontext,
 		err = -EINVAL;
 	}
 
-	if (err) {
+	if (err)
 		ibdev_dbg(
 			&dev->ibdev,
 			"Couldn't mmap address[%#llx] length[%#zx] mmap_flag[%d] err[%d]\n",
 			entry->address, rdma_entry->npages * PAGE_SIZE,
 			entry->mmap_flag, err);
-	}
 
 	rdma_user_mmap_entry_put(rdma_entry);
 	return err;
diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index 9b1fb84a3d45..e0b1238d31df 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -1685,6 +1685,14 @@ static u64 access_sw_pio_drain(const struct cntr_entry *entry,
 	return dd->verbs_dev.n_piodrain;
 }
 
+static u64 access_sw_ctx0_seq_drop(const struct cntr_entry *entry,
+				   void *context, int vl, int mode, u64 data)
+{
+	struct hfi1_devdata *dd = context;
+
+	return dd->ctx0_seq_drop;
+}
+
 static u64 access_sw_vtx_wait(const struct cntr_entry *entry,
 			      void *context, int vl, int mode, u64 data)
 {
@@ -4106,6 +4114,7 @@ def_access_ibp_counter(rc_crwaits);
 static struct cntr_entry dev_cntrs[DEV_CNTR_LAST] = {
 [C_RCV_OVF] = RXE32_DEV_CNTR_ELEM(RcvOverflow, RCV_BUF_OVFL_CNT, CNTR_SYNTH),
 [C_RX_LEN_ERR] = RXE32_DEV_CNTR_ELEM(RxLenErr, RCV_LENGTH_ERR_CNT, CNTR_SYNTH),
+[C_RX_SHORT_ERR] = RXE32_DEV_CNTR_ELEM(RxShrErr, RCV_SHORT_ERR_CNT, CNTR_SYNTH),
 [C_RX_ICRC_ERR] = RXE32_DEV_CNTR_ELEM(RxICrcErr, RCV_ICRC_ERR_CNT, CNTR_SYNTH),
 [C_RX_EBP] = RXE32_DEV_CNTR_ELEM(RxEbpCnt, RCV_EBP_CNT, CNTR_SYNTH),
 [C_RX_TID_FULL] = RXE32_DEV_CNTR_ELEM(RxTIDFullEr, RCV_TID_FULL_ERR_CNT,
@@ -4249,6 +4258,8 @@ static struct cntr_entry dev_cntrs[DEV_CNTR_LAST] = {
 			    access_sw_cpu_intr),
 [C_SW_CPU_RCV_LIM] = CNTR_ELEM("RcvLimit", 0, 0, CNTR_NORMAL,
 			    access_sw_cpu_rcv_limit),
+[C_SW_CTX0_SEQ_DROP] = CNTR_ELEM("SeqDrop0", 0, 0, CNTR_NORMAL,
+			    access_sw_ctx0_seq_drop),
 [C_SW_VTX_WAIT] = CNTR_ELEM("vTxWait", 0, 0, CNTR_NORMAL,
 			    access_sw_vtx_wait),
 [C_SW_PIO_WAIT] = CNTR_ELEM("PioWait", 0, 0, CNTR_NORMAL,
@@ -6862,7 +6873,7 @@ static void rxe_kernel_unfreeze(struct hfi1_devdata *dd)
 		}
 		rcvmask = HFI1_RCVCTRL_CTXT_ENB;
 		/* HFI1_RCVCTRL_TAILUPD_[ENB|DIS] needs to be set explicitly */
-		rcvmask |= rcd->rcvhdrtail_kvaddr ?
+		rcvmask |= hfi1_rcvhdrtail_kvaddr(rcd) ?
 			HFI1_RCVCTRL_TAILUPD_ENB : HFI1_RCVCTRL_TAILUPD_DIS;
 		hfi1_rcvctrl(dd, rcvmask, rcd);
 		hfi1_rcd_put(rcd);
@@ -8394,20 +8405,62 @@ void force_recv_intr(struct hfi1_ctxtdata *rcd)
 static inline int check_packet_present(struct hfi1_ctxtdata *rcd)
 {
 	u32 tail;
-	int present;
 
-	if (!rcd->rcvhdrtail_kvaddr)
-		present = (rcd->seq_cnt ==
-				rhf_rcv_seq(rhf_to_cpu(get_rhf_addr(rcd))));
-	else /* is RDMA rtail */
-		present = (rcd->head != get_rcvhdrtail(rcd));
-
-	if (present)
+	if (hfi1_packet_present(rcd))
 		return 1;
 
 	/* fall back to a CSR read, correct indpendent of DMA_RTAIL */
 	tail = (u32)read_uctxt_csr(rcd->dd, rcd->ctxt, RCV_HDR_TAIL);
-	return rcd->head != tail;
+	return hfi1_rcd_head(rcd) != tail;
+}
+
+/**
+ * Common code for receive contexts interrupt handlers.
+ * Update traces, increment kernel IRQ counter and
+ * setup ASPM when needed.
+ */
+static void receive_interrupt_common(struct hfi1_ctxtdata *rcd)
+{
+	struct hfi1_devdata *dd = rcd->dd;
+
+	trace_hfi1_receive_interrupt(dd, rcd);
+	this_cpu_inc(*dd->int_counter);
+	aspm_ctx_disable(rcd);
+}
+
+/**
+ * __hfi1_rcd_eoi_intr() - Make HW issue receive interrupt
+ * when there are packets present in the queue. When calling
+ * with interrupts enabled please use hfi1_rcd_eoi_intr.
+ *
+ * @rcd: valid receive context
+ */
+static void __hfi1_rcd_eoi_intr(struct hfi1_ctxtdata *rcd)
+{
+	clear_recv_intr(rcd);
+	if (check_packet_present(rcd))
+		force_recv_intr(rcd);
+}
+
+/**
+ * hfi1_rcd_eoi_intr() - End of Interrupt processing action
+ *
+ * @rcd: Ptr to hfi1_ctxtdata of receive context
+ *
+ *  Hold IRQs so we can safely clear the interrupt and
+ *  recheck for a packet that may have arrived after the previous
+ *  check and the interrupt clear.  If a packet arrived, force another
+ *  interrupt. This routine can be called at the end of receive packet
+ *  processing in interrupt service routines, interrupt service thread
+ *  and softirqs
+ */
+static void hfi1_rcd_eoi_intr(struct hfi1_ctxtdata *rcd)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__hfi1_rcd_eoi_intr(rcd);
+	local_irq_restore(flags);
 }
 
 /*
@@ -8421,13 +8474,9 @@ static inline int check_packet_present(struct hfi1_ctxtdata *rcd)
 irqreturn_t receive_context_interrupt(int irq, void *data)
 {
 	struct hfi1_ctxtdata *rcd = data;
-	struct hfi1_devdata *dd = rcd->dd;
 	int disposition;
-	int present;
 
-	trace_hfi1_receive_interrupt(dd, rcd);
-	this_cpu_inc(*dd->int_counter);
-	aspm_ctx_disable(rcd);
+	receive_interrupt_common(rcd);
 
 	/* receive interrupt remains blocked while processing packets */
 	disposition = rcd->do_interrupt(rcd, 0);
@@ -8440,17 +8489,7 @@ irqreturn_t receive_context_interrupt(int irq, void *data)
 	if (disposition == RCV_PKT_LIMIT)
 		return IRQ_WAKE_THREAD;
 
-	/*
-	 * The packet processor detected no more packets.  Clear the receive
-	 * interrupt and recheck for a packet packet that may have arrived
-	 * after the previous check and interrupt clear.  If a packet arrived,
-	 * force another interrupt.
-	 */
-	clear_recv_intr(rcd);
-	present = check_packet_present(rcd);
-	if (present)
-		force_recv_intr(rcd);
-
+	__hfi1_rcd_eoi_intr(rcd);
 	return IRQ_HANDLED;
 }
 
@@ -8461,24 +8500,11 @@ irqreturn_t receive_context_interrupt(int irq, void *data)
 irqreturn_t receive_context_thread(int irq, void *data)
 {
 	struct hfi1_ctxtdata *rcd = data;
-	int present;
 
 	/* receive interrupt is still blocked from the IRQ handler */
 	(void)rcd->do_interrupt(rcd, 1);
 
-	/*
-	 * The packet processor will only return if it detected no more
-	 * packets.  Hold IRQs here so we can safely clear the interrupt and
-	 * recheck for a packet that may have arrived after the previous
-	 * check and the interrupt clear.  If a packet arrived, force another
-	 * interrupt.
-	 */
-	local_irq_disable();
-	clear_recv_intr(rcd);
-	present = check_packet_present(rcd);
-	if (present)
-		force_recv_intr(rcd);
-	local_irq_enable();
+	hfi1_rcd_eoi_intr(rcd);
 
 	return IRQ_HANDLED;
 }
@@ -10049,7 +10075,7 @@ u32 lrh_max_header_bytes(struct hfi1_devdata *dd)
 	 * the first kernel context would have been allocated by now so
 	 * we are guaranteed a valid value.
 	 */
-	return (dd->rcd[0]->rcvhdrqentsize - 2/*PBC/RHF*/ + 1/*ICRC*/) << 2;
+	return (get_hdrqentsize(dd->rcd[0]) - 2/*PBC/RHF*/ + 1/*ICRC*/) << 2;
 }
 
 /*
@@ -10094,7 +10120,7 @@ static void set_send_length(struct hfi1_pportdata *ppd)
 		thres = min(sc_percent_to_threshold(dd->vld[i].sc, 50),
 			    sc_mtu_to_threshold(dd->vld[i].sc,
 						dd->vld[i].mtu,
-						dd->rcd[0]->rcvhdrqentsize));
+						get_hdrqentsize(dd->rcd[0])));
 		for (j = 0; j < INIT_SC_PER_VL; j++)
 			sc_set_cr_threshold(
 					pio_select_send_context_vl(dd, j, i),
@@ -11821,7 +11847,7 @@ u32 hdrqempty(struct hfi1_ctxtdata *rcd)
 	head = (read_uctxt_csr(rcd->dd, rcd->ctxt, RCV_HDR_HEAD)
 		& RCV_HDR_HEAD_HEAD_SMASK) >> RCV_HDR_HEAD_HEAD_SHIFT;
 
-	if (rcd->rcvhdrtail_kvaddr)
+	if (hfi1_rcvhdrtail_kvaddr(rcd))
 		tail = get_rcvhdrtail(rcd);
 	else
 		tail = read_uctxt_csr(rcd->dd, rcd->ctxt, RCV_HDR_TAIL);
@@ -11865,6 +11891,84 @@ static u32 encoded_size(u32 size)
 	return 0x1;	/* if invalid, go with the minimum size */
 }
 
+/**
+ * encode_rcv_header_entry_size - return chip specific encoding for size
+ * @size: size in dwords
+ *
+ * Convert a receive header entry size that to the encoding used in the CSR.
+ *
+ * Return a zero if the given size is invalid, otherwise the encoding.
+ */
+u8 encode_rcv_header_entry_size(u8 size)
+{
+	/* there are only 3 valid receive header entry sizes */
+	if (size == 2)
+		return 1;
+	if (size == 16)
+		return 2;
+	if (size == 32)
+		return 4;
+	return 0; /* invalid */
+}
+
+/**
+ * hfi1_validate_rcvhdrcnt - validate hdrcnt
+ * @dd: the device data
+ * @thecnt: the header count
+ */
+int hfi1_validate_rcvhdrcnt(struct hfi1_devdata *dd, uint thecnt)
+{
+	if (thecnt <= HFI1_MIN_HDRQ_EGRBUF_CNT) {
+		dd_dev_err(dd, "Receive header queue count too small\n");
+		return -EINVAL;
+	}
+
+	if (thecnt > HFI1_MAX_HDRQ_EGRBUF_CNT) {
+		dd_dev_err(dd,
+			   "Receive header queue count cannot be greater than %u\n",
+			   HFI1_MAX_HDRQ_EGRBUF_CNT);
+		return -EINVAL;
+	}
+
+	if (thecnt % HDRQ_INCREMENT) {
+		dd_dev_err(dd, "Receive header queue count %d must be divisible by %lu\n",
+			   thecnt, HDRQ_INCREMENT);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * set_hdrq_regs - set header queue registers for context
+ * @dd: the device data
+ * @ctxt: the context
+ * @entsize: the dword entry size
+ * @hdrcnt: the number of header entries
+ */
+void set_hdrq_regs(struct hfi1_devdata *dd, u8 ctxt, u8 entsize, u16 hdrcnt)
+{
+	u64 reg;
+
+	reg = (((u64)hdrcnt >> HDRQ_SIZE_SHIFT) & RCV_HDR_CNT_CNT_MASK) <<
+	      RCV_HDR_CNT_CNT_SHIFT;
+	write_kctxt_csr(dd, ctxt, RCV_HDR_CNT, reg);
+	reg = ((u64)encode_rcv_header_entry_size(entsize) &
+	       RCV_HDR_ENT_SIZE_ENT_SIZE_MASK) <<
+	      RCV_HDR_ENT_SIZE_ENT_SIZE_SHIFT;
+	write_kctxt_csr(dd, ctxt, RCV_HDR_ENT_SIZE, reg);
+	reg = ((u64)DEFAULT_RCVHDRSIZE & RCV_HDR_SIZE_HDR_SIZE_MASK) <<
+	      RCV_HDR_SIZE_HDR_SIZE_SHIFT;
+	write_kctxt_csr(dd, ctxt, RCV_HDR_SIZE, reg);
+
+	/*
+	 * Program dummy tail address for every receive context
+	 * before enabling any receive context
+	 */
+	write_kctxt_csr(dd, ctxt, RCV_HDR_TAIL_ADDR,
+			dd->rcvhdrtail_dummy_dma);
+}
+
 void hfi1_rcvctrl(struct hfi1_devdata *dd, unsigned int op,
 		  struct hfi1_ctxtdata *rcd)
 {
@@ -11886,13 +11990,13 @@ void hfi1_rcvctrl(struct hfi1_devdata *dd, unsigned int op,
 		/* reset the tail and hdr addresses, and sequence count */
 		write_kctxt_csr(dd, ctxt, RCV_HDR_ADDR,
 				rcd->rcvhdrq_dma);
-		if (rcd->rcvhdrtail_kvaddr)
+		if (hfi1_rcvhdrtail_kvaddr(rcd))
 			write_kctxt_csr(dd, ctxt, RCV_HDR_TAIL_ADDR,
 					rcd->rcvhdrqtailaddr_dma);
-		rcd->seq_cnt = 1;
+		hfi1_set_seq_cnt(rcd, 1);
 
 		/* reset the cached receive header queue head value */
-		rcd->head = 0;
+		hfi1_set_rcd_head(rcd, 0);
 
 		/*
 		 * Zero the receive header queue so we don't get false
@@ -11972,7 +12076,7 @@ void hfi1_rcvctrl(struct hfi1_devdata *dd, unsigned int op,
 			      IS_RCVAVAIL_START + rcd->ctxt, false);
 		rcvctrl &= ~RCV_CTXT_CTRL_INTR_AVAIL_SMASK;
 	}
-	if ((op & HFI1_RCVCTRL_TAILUPD_ENB) && rcd->rcvhdrtail_kvaddr)
+	if ((op & HFI1_RCVCTRL_TAILUPD_ENB) && hfi1_rcvhdrtail_kvaddr(rcd))
 		rcvctrl |= RCV_CTXT_CTRL_TAIL_UPD_SMASK;
 	if (op & HFI1_RCVCTRL_TAILUPD_DIS) {
 		/* See comment on RcvCtxtCtrl.TailUpd above */
diff --git a/drivers/infiniband/hw/hfi1/chip.h b/drivers/infiniband/hw/hfi1/chip.h
index 4ca5ac8d7e9e..725509261016 100644
--- a/drivers/infiniband/hw/hfi1/chip.h
+++ b/drivers/infiniband/hw/hfi1/chip.h
@@ -358,6 +358,8 @@
 #define MAX_EAGER_BUFFER       (256 * 1024)
 #define MAX_EAGER_BUFFER_TOTAL (64 * (1 << 20)) /* max per ctxt 64MB */
 #define MAX_EXPECTED_BUFFER    (2048 * 1024)
+#define HFI1_MIN_HDRQ_EGRBUF_CNT 32
+#define HFI1_MAX_HDRQ_EGRBUF_CNT 16352
 
 /*
  * Receive expected base and count and eager base and count increment -
@@ -699,6 +701,10 @@ static inline u32 chip_rcv_array_count(struct hfi1_devdata *dd)
 	return read_csr(dd, RCV_ARRAY_CNT);
 }
 
+u8 encode_rcv_header_entry_size(u8 size);
+int hfi1_validate_rcvhdrcnt(struct hfi1_devdata *dd, uint thecnt);
+void set_hdrq_regs(struct hfi1_devdata *dd, u8 ctxt, u8 entsize, u16 hdrcnt);
+
 u64 create_pbc(struct hfi1_pportdata *ppd, u64 flags, int srate_mbs, u32 vl,
 	       u32 dw_len);
 
@@ -859,6 +865,7 @@ static inline int idx_from_vl(int vl)
 enum {
 	C_RCV_OVF = 0,
 	C_RX_LEN_ERR,
+	C_RX_SHORT_ERR,
 	C_RX_ICRC_ERR,
 	C_RX_EBP,
 	C_RX_TID_FULL,
@@ -926,6 +933,7 @@ enum {
 	C_DC_PG_STS_TX_MBE_CNT,
 	C_SW_CPU_INTR,
 	C_SW_CPU_RCV_LIM,
+	C_SW_CTX0_SEQ_DROP,
 	C_SW_VTX_WAIT,
 	C_SW_PIO_WAIT,
 	C_SW_PIO_DRAIN,
diff --git a/drivers/infiniband/hw/hfi1/chip_registers.h b/drivers/infiniband/hw/hfi1/chip_registers.h
index ab3589d17aee..fb3ec9bff7a2 100644
--- a/drivers/infiniband/hw/hfi1/chip_registers.h
+++ b/drivers/infiniband/hw/hfi1/chip_registers.h
@@ -381,6 +381,7 @@
 #define DC_LCB_STS_LINK_TRANSFER_ACTIVE (DC_LCB_CSRS + 0x000000000468)
 #define DC_LCB_STS_ROUND_TRIP_LTP_CNT (DC_LCB_CSRS + 0x0000000004B0)
 #define RCV_LENGTH_ERR_CNT 0
+#define RCV_SHORT_ERR_CNT 2
 #define RCV_ICRC_ERR_CNT 6
 #define RCV_EBP_CNT 9
 #define RCV_BUF_OVFL_CNT 10
diff --git a/drivers/infiniband/hw/hfi1/common.h b/drivers/infiniband/hw/hfi1/common.h
index d47da7b0438f..40a1ff0c8a8e 100644
--- a/drivers/infiniband/hw/hfi1/common.h
+++ b/drivers/infiniband/hw/hfi1/common.h
@@ -323,6 +323,9 @@ struct diag_pkt {
 /* RHF receive type error - bypass packet errors */
 #define RHF_RTE_BYPASS_NO_ERR		0x0
 
+/* MAX RcvSEQ */
+#define RHF_MAX_SEQ 13
+
 /* IB - LRH header constants */
 #define HFI1_LRH_GRH 0x0003      /* 1. word of IB LRH - next header: GRH */
 #define HFI1_LRH_BTH 0x0002      /* 1. word of IB LRH - next header: BTH */
diff --git a/drivers/infiniband/hw/hfi1/debugfs.c b/drivers/infiniband/hw/hfi1/debugfs.c
index d268bf9c42ee..4633a0ce1a8c 100644
--- a/drivers/infiniband/hw/hfi1/debugfs.c
+++ b/drivers/infiniband/hw/hfi1/debugfs.c
@@ -379,7 +379,7 @@ static void *_rcds_seq_next(struct seq_file *s, void *v, loff_t *pos)
 	struct hfi1_devdata *dd = dd_from_dev(ibd);
 
 	++*pos;
-	if (!dd->rcd || *pos >= dd->n_krcv_queues)
+	if (!dd->rcd || *pos >= dd->num_rcv_contexts)
 		return NULL;
 	return pos;
 }
diff --git a/drivers/infiniband/hw/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c
index 01aa1f132f55..049d15befe58 100644
--- a/drivers/infiniband/hw/hfi1/driver.c
+++ b/drivers/infiniband/hw/hfi1/driver.c
@@ -411,14 +411,14 @@ drop:
 static inline void init_packet(struct hfi1_ctxtdata *rcd,
 			       struct hfi1_packet *packet)
 {
-	packet->rsize = rcd->rcvhdrqentsize; /* words */
-	packet->maxcnt = rcd->rcvhdrq_cnt * packet->rsize; /* words */
+	packet->rsize = get_hdrqentsize(rcd); /* words */
+	packet->maxcnt = get_hdrq_cnt(rcd) * packet->rsize; /* words */
 	packet->rcd = rcd;
 	packet->updegr = 0;
 	packet->etail = -1;
 	packet->rhf_addr = get_rhf_addr(rcd);
 	packet->rhf = rhf_to_cpu(packet->rhf_addr);
-	packet->rhqoff = rcd->head;
+	packet->rhqoff = hfi1_rcd_head(rcd);
 	packet->numpkt = 0;
 }
 
@@ -551,22 +551,22 @@ static inline void init_ps_mdata(struct ps_mdata *mdata,
 	mdata->maxcnt = packet->maxcnt;
 	mdata->ps_head = packet->rhqoff;
 
-	if (HFI1_CAP_KGET_MASK(rcd->flags, DMA_RTAIL)) {
+	if (get_dma_rtail_setting(rcd)) {
 		mdata->ps_tail = get_rcvhdrtail(rcd);
 		if (rcd->ctxt == HFI1_CTRL_CTXT)
-			mdata->ps_seq = rcd->seq_cnt;
+			mdata->ps_seq = hfi1_seq_cnt(rcd);
 		else